State of the Art on Diffusion Models for Visual Computing

Simple item page
dc.contributor.authorPo, Ryanen_US
dc.contributor.authorYifan, Wangen_US
dc.contributor.authorGolyanik, Vladislaven_US
dc.contributor.authorAberman, Kfiren_US
dc.contributor.authorBarron, Jon T.en_US
dc.contributor.authorBermano, Amiten_US
dc.contributor.authorChan, Ericen_US
dc.contributor.authorDekel, Talien_US
dc.contributor.authorHolynski, Aleksanderen_US
dc.contributor.authorKanazawa, Angjooen_US
dc.contributor.authorLiu, C. Karenen_US
dc.contributor.authorLiu, Lingjieen_US
dc.contributor.authorMildenhall, Benen_US
dc.contributor.authorNießner, Matthiasen_US
dc.contributor.authorOmmer, Björnen_US
dc.contributor.authorTheobalt, Christianen_US
dc.contributor.authorWonka, Peteren_US
dc.contributor.authorWetzstein, Gordonen_US
dc.contributor.editorAristidou, Andreasen_US
dc.contributor.editorMacdonnell, Rachelen_US
dc.date.accessioned2024-04-30T09:03:17Z
dc.date.available2024-04-30T09:03:17Z
dc.date.issued2024
dc.description.abstractThe field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion-based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state-of-the-art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion-based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.en_US
dc.description.documenttypestar
dc.description.number2
dc.description.sectionheadersState of the Art Reports
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15063
dc.identifier.issn1467-8659
dc.identifier.pages34 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15063
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15063
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Computer graphics; Neural networks
dc.subjectComputing methodologies → Computer graphics
dc.subjectNeural networks
dc.titleState of the Art on Diffusion Models for Visual Computingen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
v43i2star_04_15063.pdf
Size:
25.76 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2024 - STARs (CGF 43-2)
STAR collection (since 2024)